{"as_of":"2026-08-04T21:24:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:2725b1bb5d249781dea3498ece5cbaaa427aaa9a5f199abc9e7343f541079b11","coverage":[{"denominator":0,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":2,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":2,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-04T06:34:03.388597+00:00","state":"measured"},{"denominator":2,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":2,"source":"paper_references, paper_reference_links","source_observed_at":"2026-05-11T01:44:31.308036Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-05-11T18:46:09.374587Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2304.00571","last_updated":"2025-04-04T15:53:08Z","snapshot_observed_at":"2026-07-06T15:11:04.139563Z","submitted_at":"2023-04-02T16:40:42Z","title":"DropMAE: Learning Representations via Masked Autoencoders with Spatial-Attention Dropout for Temporal Matching Tasks","version":3},"cited_work":{"arxiv_id":"2304.00571","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2304.00571","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"79aeae8a-96f4-4e27-8a7f-d6a358cb04f7","year":2023},"citing_paper":{"arxiv_id":"2605.06092","last_updated":"2026-05-07T12:12:28Z","snapshot_observed_at":"2026-07-31T08:48:26.371647Z","submitted_at":"2026-05-07T12:12:28Z","title":"Boosting Self-Supervised Tracking with Contextual Prompts and Noise Learning","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-05-08T14:02:46.701221Z"},"links":{"cited_paper":"/paper/2304.00571","citing_paper":"/paper/2605.06092"},"observation_digest":"sha256:78db7ac3d4bb043baed59b78fcc300dd33d64581c5602610e27d40ee7b77dee1","observation_id":"11e80ae9-f2a0-47cf-9d2c-7f93e63a8876","resolution":{"observed_at":"2026-05-11T18:46:09.376649Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2304.00571","last_updated":"2025-04-04T15:53:08Z","snapshot_observed_at":"2026-07-06T15:11:04.139563Z","submitted_at":"2023-04-02T16:40:42Z","title":"DropMAE: Learning Representations via Masked Autoencoders with Spatial-Attention Dropout for Temporal Matching Tasks","version":3},"cited_work":{"arxiv_id":"2304.00571","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2304.00571","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"79aeae8a-96f4-4e27-8a7f-d6a358cb04f7","year":2023},"citing_paper":{"arxiv_id":"2605.07064","last_updated":"2026-05-08T00:17:09Z","snapshot_observed_at":"2026-08-02T10:29:52.926870Z","submitted_at":"2026-05-08T00:17:09Z","title":"Learning to Track Instance from Single Nature Language Description","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-05-11T01:44:31.308036Z"},"links":{"cited_paper":"/paper/2304.00571","citing_paper":"/paper/2605.07064"},"observation_digest":"sha256:fa18149e95b97a901bcd727328e212e15fee5cb7d29d5c62364ca551f56b5169","observation_id":"914c681f-6b2b-4ca3-a2b8-b1d4d1d945e7","resolution":{"observed_at":"2026-05-11T01:45:51.052834Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2304.00571/citation-record","integrity":"/paper/2304.00571/integrity","json":"/paper/2304.00571/citation-record.json","paper":"/paper/2304.00571"},"outbound":[],"paper":{"arxiv_id":"2304.00571","last_updated":"2025-04-04T15:53:08Z","latest_version":3,"primary_category":"cs.CV","snapshot_observed_at":"2026-07-06T15:11:04.139563Z","submitted_at":"2023-04-02T16:40:42Z","title":"DropMAE: Learning Representations via Masked Autoencoders with Spatial-Attention Dropout for Temporal Matching Tasks"},"reference_resolution":{"displayed":0,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":0,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":0},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"thesis":"As of 4 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2304.00571."}